Model trainer/creator: kblueleaf
Uploaded to MoescapeA by Laanver Phi
[Please view the full model detail on CivitAI]
rev1 Source: https://civitai.com/models/399873?modelVersionId=445973
rev2 Source: https://civitai.com/models/399873?modelVersionId=546178
*Please check the [Usage1] and [Usage2] page to see how to use to checkpoint. Check [Models1] and [Models2] for understanding of the difference between versions. Check [Others] and for other details. Generally check the CivitAI page for complete breakdown.
Kohaku' XL εpsilon:
The best example of tuning t2i model at home with consumer-level hardware
join us: https://discord.gg/tPBsKDyRR5
Introduction:
Kohaku--- - XL Epsilon, the fifth major iteration in the Kohaku XL series, features a 5.2 million images dataset, LyCORIS fine-tuning[1], trained on comsumer-level hardware, and is fully open-sourced.
Benchmark: *please check the CivitAI page for the graph.
CCIP score on 3600 characters. (0~1, higher is better). Clearly, Kohaku XL Epsilon is way better than Kohaku XL Delta
Description
Tags:
All the danbooru tags with at least 1000 popularity should work. All the danbooru tags with at least 100 popularity can possibly work with high emphasis. Remember to remove all the underscore in tags. (Underscores in short tags are not be removed, which are very likely part of emoji tags.)
Remember to use 'xxx\(yyy\)' when tag have bracket and you are using sd-webui.
Special Tags:
- Quality tags: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality
- Rating tags: safe, sensitive, nsfw, explicit
- Date tags: newest, recent, mid, early, old
Quality Tags:
Quality tags are assigned based on the percentile rankings of the favorite count (fav_count) within each rating category to avoid bias on nsfw content (Animagine XL v3 have met this problem), organized from high to low as follows: 90th, 75th, 60th, 45th, 30th, and 10th percentiles. This creates seven distinct quality levels separated by six thresholds. I lower the threshold since I found that the average quality of images in Danbooru is higher than I expected.
Rating tags:
- General: safe
- Sensitive: sensitive
- Questionable: nsfw
- Explicit: nsfw, explicit
Note: During training, content tagged as "explicit" is also considered under "nsfw" to ensure a comprehensive understanding.
Date tags:
Date tags are based on the upload dates of the images, as the metadata does not include the actual creation dates.
The periods are categorized as follows:
- 2005~2010: old
- 2011~2014: early
- 2015~2017: mid
- 2018~2020: recent
- 2021~2024: newest
Resolution:
This model is trained for resolutions from ARB 1024x1024 with minimum resolution 256 and maximum resolution 4096. This means you can use the standard SDXL resolution. However, opting for a slightly higher resolution than 1024x1024 is recommended. Applying a hires-fix is also suggested for better results. For more information, please check out the sample images provided.
FAQ
kohaku
xl
sdxl
style
epsilon
trained
checkpoint
sdxl1.0
trainedcheckpoint
trained_checkpoint
trained-checkpoint
checkpoint_trained
checkpointtrained
checkpoint-trained
kblueleaf
epsilonversion
versionepsilon
epsilon-version
epsilon_version
version-epsilon
version_epsilon
kohaku-xlepsilon
kohakuxl
kohaku_xl
kohaku-xl
kohaku-xl-epsilon
kohaku-xl_epsilon
Details
Downloads
686
Platform
Moescape
Platform Status
Available
Created
11/4/2024
Updated
11/4/2024
Deleted
-
Files
Available On (15 platforms)
Same model published on other platforms. May have additional downloads or version variants.
SeaArt
Kohaku-XL Epsilon - rev1Moescape
Kohaku-XL Epsilon - [Usage1]Moescape
Kohaku-XL Epsilon - [Usage2]Moescape
Kohaku-XL Epsilon - [Model1]Moescape
Kohaku-XL Epsilon - [Model2]Moescape
Kohaku-XL Epsilon - [Others]Moescape
Kohaku-XL Epsilon - rev1Moescape
Kohaku-XL Epsilon - rev2Yodayo
Kohaku-XL Epsilon - [Usage1]Yodayo
Kohaku-XL Epsilon - [Usage2]Yodayo
Kohaku-XL Epsilon - [Model1]Yodayo
Kohaku-XL Epsilon - [Model2]Yodayo
Kohaku-XL Epsilon - [Others]Yodayo
Kohaku-XL Epsilon - rev1Yodayo
Kohaku-XL Epsilon - rev2